Generative Training
Denoising Score Matching
Introduced by Song et al. in Generative Modeling by Estimating Gradients of the Data DistributionTraining a denoiser on signals gives you a powerful prior over this signal that you can then use to sample examples of this signal.
Source: Generative Modeling by Estimating Gradients of the Data DistributionPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Denoising | 22 | 48.89% |
| Image Generation | 6 | 13.33% |
| Time Series Analysis | 2 | 4.44% |
| Time Series Forecasting | 2 | 4.44% |
| Image Inpainting | 2 | 4.44% |
| Drug Discovery | 1 | 2.22% |
| Disentanglement | 1 | 2.22% |
| Speech Synthesis | 1 | 2.22% |
| Compressive Sensing | 1 | 2.22% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
